基于注意力机制的卷积神经网络机械钻速预测方法
作者:
中图分类号:

TE242

基金项目:

中国石化科技攻关项目(P17049-3)


Prediction Method for ROP Based on Attention Mechanism of Convolutional Neural Network
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    传统机器学习方法在进行机械钻速预测时,受复杂特征提取和人为认知局限性的影响,难以满足现场预测精度要求。基于此,提出一种特征提取和回归预测相结合的机械钻速预测方法。首先,采用箱型图和独热编码对钻井实测数据进行预处理,清除异常数据并将离散特征连续化。其次,应用卷积神经网络(convolutional neural network, CNN)挖掘数据特征,并在网络中引入通道注意力机制(squeeze-and-excitation network, SENet),实现对CNN特征通道重要性程度的合理分配,建立SE-CNN机械钻速预测模型。最后,将SE-CNN模型与CNN模型进行对比分析,结果表明:SE-CNN模型的拟合优度提高了2.1%,平均绝对误差和均方根误差分别降低了1.1%和1.5%。SE-CNN模型具有较高的预测精度,可以用于现场机械钻速预测,为钻井提速提供科学参考。

    Abstract:

    Traditional machine learning methods for mechanical ROP prediction are affected by complex feature extraction and imitations of human understanding, which make the prediction accuracy difficult to meet the on-site demand. Based on this, a new ROP prediction method combining feature extraction and regression prediction was proposed. Firstly, data in drilling engineering were pre-processed by box-plot method and one-hot encoding to eliminate abnormal data and to make discrete characteristic continuous. Secondly, convolutional neural network (CNN) was applied to extracting data features, and channel attention mechanism (squeeze-and-excitation network, SENet) was introduced to construct an SE-CNN model, which could adjust the importance of CNN feature channel. Finally, and SE-CNN model was compared with CNN model. The results shows that the goodness of fit of SE-CNN model is increased by 2.1%, the mean absolute error and the root mean squared error are decreased by 1.1% and 1.5%. SE-CNN model has a good prediction accuracy, SE-CNN model can forecast the ROP of drilling field and provides a scientific reference for increasing the ROP during drilling.

    参考文献
    相似文献
    引证文献
引用本文

李博志,杨明合,许楷,等. 基于注意力机制的卷积神经网络机械钻速预测方法[J]. 科学技术与工程, 2024, 24(21): 8910-8916.
Li Bozhi, Yang Minghe, Xu Kai, et al. Prediction Method for ROP Based on Attention Mechanism of Convolutional Neural Network[J]. Science Technology and Engineering,2024,24(21):8910-8916.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-08-01
  • 最后修改日期:2024-07-17
  • 录用日期:2023-12-02
  • 在线发布日期: 2024-08-14
×
一元复始,万象更新。祝作者朋友 元旦快乐!
喜报!《科学技术与工程》5篇文章入选中国科协“2024年度科技期刊双语传播工程”项目